TY - CHAP TI - Understanding Which Graph Depictions Are Best for Viewers AU - Christensen, Johanne AU - Bae, Ju Hee AU - Watson, Ben AU - Rappa, Micheal T2 - Smart Graphics AB - We use data from a study of three different graph depictions: node-link, centered matrix, and quilts to explore how pathfinding time is influenced by the graph structure, measured by the number of nodes, links, skips and layers. We use regressions to determine the influence of these attributes. Furthering this idea, we begin to explore how individual users navigate through graphs. PY - 2014/// DO - 10.1007/978-3-319-11650-1_17 SP - 174-177 OP - PB - Springer International Publishing SN - 9783319116495 9783319116501 UR - http://dx.doi.org/10.1007/978-3-319-11650-1_17 DB - Crossref ER - TY - JOUR TI - Visualizing likelihood density functions via optimal region projection AU - Canary, Hal AU - Taylor, Russell M., II AU - Quammen, Cory AU - Pratt, Scott AU - Gomez, Facundo A. AU - O'Shea, Brian AU - Healey, Christopher G. T2 - COMPUTERS & GRAPHICS-UK AB - Abstract Effective visualization of high-likelihood regions of parameter space is severely hampered by the large number of parameter dimensions that many models have. We present a novel technique, Optimal Percentile Region Projection, to visualize a high-dimensional likelihood density function that enables the viewer to understand the shape of the high-likelihood region. Optimal Percentile Region Projection has three novel components: first, we select the region of high likelihood in the high-dimensional space before projecting its shadow into a lower-dimensional projected space. Second, we analyze features on the surface of the region in the projected space to select the projection direction that shows the most interesting parameter dependencies. Finally, we use a three-dimensional projection space to show features that are not salient in only two dimensions. The viewer can also choose sets of axes to project along to explore subsets of the parameter space, using either the original parameter axes or principal-component axes. The technique was evaluated by our domain-science collaborators, who found it to be superior to their existing workflow both when there were interesting dependencies between parameters and when there were not. DA - 2014/6// PY - 2014/6// DO - 10.1016/j.cag.2014.02.005 VL - 41 SP - 62-71 SN - 1873-7684 KW - Uncertainty KW - Parameter space analysis KW - Visualization KW - Likelihood density function ER -